AI agents call get_trending_videos to retrieve information from Iqiyi without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns trending video metadata from iQiyi. There is no indication of data modification, deletion, code execution, or financial impact. It is a straightforward retrieval operation that produces no side effects on the underlying system or data store.
From the tool's definition Tool fetches trending videos 'based on play count' — a retrieval operation with no stated side effects. The server description confirms it is for 'accessing iQiyi API to fetch new releases and trending videos,' indicating read-only data retrieval.
Attacks that exploit this kind of access
Get trending videos based on play count. It is categorised as a Read tool in the Iqiyi MCP Server, which means it retrieves data without modifying state.
Register the Iqiyi MCP server in PolicyLayer and add a rule for get_trending_videos: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Iqiyi. Nothing to install.
get_trending_videos is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_trending_videos rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_trending_videos. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_trending_videos is provided by the Iqiyi MCP server (zhangya0/mcp-server-iqiyi). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →